© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74721
    Prev
    Next
    INDEX
    Explanations

    Iceland

    np_max-act · gemini-2.0-flash

    This neuron detects Iceland-related proper nouns and place names (e.g., “Reykjavík,” “Iceland,” Icelandic personal/place names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */
↵
↵
    -0.07
     knife
    -0.07
     summarized
    -0.06
     استر
    -0.06
     knives
    -0.06
    ячи
    -0.06
    Za
    -0.06
    Kent
    -0.06
     Knife
    -0.06
     fighter
    -0.06
    POSITIVE LOGITS
     Iceland
    0.10
     Icelandic
    0.08
    celand
    0.07
    sson
    0.06
    ιλο
    0.06
    eum
    0.06
    .logic
    0.06
     vypad
    0.06
    rem
    0.06
    供
    0.06
    Activations Density 0.007%

    No Known Activations